Skip to content

Peruvian

A living, breathing guide to the food, the travel, the craftsmanship, and the heritage that defines being Peruvian

I'm a product designer from Lima, Peru, and Peruvian is my way of sharing the depth, warmth, and beauty of our culture with the world.

The Peruvian homepage: “What it means to be Peruvian.” over a line map of Peru, a button to the welcome letter from the founder, and four ways in: Eat & Drink, Places, Heritage and Made in Peru

Peruvian is a deeply personal passion project. I built it with AI agents, deciding what Peruvian should be, turning that point of view into rules, and learning which decisions I could delegate and which still needed me.

It is a growing catalog of the food, places, languages, and crafts that shape Peruvian culture. It keeps the original Spanish and Quechua names intact and gives each subject enough room to be understood on its own.

peruvian.com
Role
Product designer, builder, founder
Timeline
October – November 2026
Models
Claude (copy, taste, and review), Gemini (structural logic), lighter models (wiring and operations)
Status
Live in English; Spanish edition currently in progress.

01 / ORIGIN

Giving the idea a purpose

"Peruvian" is a large word. I needed to decide what the site could honestly do without flattening an entire culture into a slogan.

My family is Peruvian, and the site is about our culture. I talked the idea through with them because their reactions were part of deciding what felt true, what felt reductive, and what was worth making.

I also own IncaTrail.com and Saborear.com. I built Peruvian as a funnel that works both ways: readers can move from here to travel or cook, while IncaTrail and Saborear can send them back here to learn more. That strategy is why outbound links are part of the experience, never ads.

02 / EXPERIENCE

Refining what the agents made

The site at first opened with a call to action to explore the site. A personal welcome was the better way to earn trust and invite people onto the journey while I figure it out. Now it opens with an invitation to read an open letter from me, its founder.

Peruvian on a phone: the dark hero with a line map of Peru, “What it means to be Peruvian.” and a button reading “A Welcome Letter from Our Founder”
The homepage now opens with an invitation to read my letter.

03 / WORKFLOW

Learning where judgment belongs

I turned the product intent into a brief the agents could follow and the tests could inspect. The workflow changed whenever an agent exposed a gap between speed and judgment.

  • Routing: I chose Grok 4.7 for operational work to manage cost, then switched to Fable to assess which model should handle each kind of task. Lighter models now handle repetition and syntax; reasoning models handle voice, taste, the brief, and test design.
  • Template: One content schema and one entry component give repetitive work a fixed shape, which makes it easy to delegate and makes deviations obvious.
  • Secrets: Keys live outside the checkout and outside the model's context; the first botched handoff became the rule to prepare secret files before they are needed.
  • Language: I built a language switcher to share across all three properties, Peruvian, Inca Trail and Saborear. English is reviewed and approved before it is translated into Spanish.

Peruvian carries sentimental weight, and follows a practical standard for working with agents: make the intent explicit, inspect the places where judgment matters, and turn failures into better rules for the next pass.

The product can grow one entry and one language at a time without giving up the care that made it personal.

From idea to production, with AI as a collaborator.

Glossy black robot character with glowing eyes

Discover

Understand the problem

  1. Step 1: Frame the idea

    Problem, audience, desired outcome

  2. Step 2: Explore together

    Questions, alternatives, tradeoffs

  3. Step 3: Validate assumptions

    Research, feasibility, evidence (AI research - I decide)

Define

Set the direction

  1. Step 4: Define the product

    Requirements and success criteria

  2. Step 5: Plan the work

    Milestones, tasks, acceptance tests. AI drafts

  3. Step 6: Approve the plan

    I revise scope before work begins. My approval.

Deliver

Build, verify, release

  1. Step 7: Build + review loop

    Implement, agent audit, fix, recheck (AI and agents)

  2. Step 8: Connect + test

    Services, env setup, staging QA

  3. Step 9: Ship + learn

    I approve release; we iterate. My approval

I use AI throughout the product development process, from exploring an idea and challenging assumptions to defining requirements, building, and reviewing the implementation.

But I don’t want a model that simply agrees with me. I expect it to question decisions, identify tradeoffs, and provide evidence that the work actually functions.

I review the plan, direct the experience, and use independent agents to help verify the implementation. Before release, I test the product and make the final call.

AI makes it possible to move much faster. My responsibility is making sure we’re moving in the right direction.